TY - JOUR

T1 - Influence of the transfer function of the NARX network hidden layer on the accuracy of predicting the changes in the surface methane concentration

AU - Medvedev, Alexander

AU - Sergeev, Alexander

AU - Buevich, Alexander

AU - Shichkin, Andrey

AU - Sergeeva, Marina

PY - 2023

Y1 - 2023

N2 - A comparison was made of the main transfer functions in the hidden layer of a nonlinear autoregressive neural network with an external input (NARX) to predict changes in the methane content in the surface layer of atmospheric air. Four transfer functions were used: S-type transfer function (LS), S-type hyperbolic tangent transfer function (TS), radial basis transfer function (RB), rectified linear units (LReLU). In general, all models were good at predicting changes in surface methane concentration. The most accurate results were obtained by the model, which using the RB type transfer function.

AB - A comparison was made of the main transfer functions in the hidden layer of a nonlinear autoregressive neural network with an external input (NARX) to predict changes in the methane content in the surface layer of atmospheric air. Four transfer functions were used: S-type transfer function (LS), S-type hyperbolic tangent transfer function (TS), radial basis transfer function (RB), rectified linear units (LReLU). In general, all models were good at predicting changes in surface methane concentration. The most accurate results were obtained by the model, which using the RB type transfer function.

UR - http://www.scopus.com/inward/record.url?partnerID=8YFLogxK&scp=85176778883

U2 - 10.1063/5.0162646

DO - 10.1063/5.0162646

M3 - Conference article

VL - 2849

JO - AIP Conference Proceedings

JF - AIP Conference Proceedings

SN - 0094-243X

IS - 1

M1 - 090025

ER -